基于成像高光谱的小麦冠层白粉病早期监测方法

doi:10.3864/j.issn.0578-1752.2022.06.005

Abstract

Abstract:

【Objective】In this study, the near-ground imaging spectrometer was used to obtain time-series images of wheat canopy after inoculation with powdery mildew, which aimed to explore the ability and performance of the combination of spectral feature and texture feature in the early detection of wheat powdery mildew at canopy scale. 【Method】 Based on the field trials of wheat varieties with different disease resistance in different years, the wavelet features sensitive to wheat powdery mildew were extracted by continuous wavelet transform (CWT) method, and the corresponding texture features were extracted based on spectral features to construct normalized difference texture index (NDTI). Meanwhile, the representative traditional vegetation indices (Vis) were selected. Then, based on these features and combinations, the partial least squares discriminant analysis (PLS-LDA) model was used to establish wheat canopy healthy and disease recognition model. The partial least squares regression (PLSR) was used to estimate the severity of wheat canopy disease. The technique was used to distinguish the healthy and disease wheat at different days after inoculation based on the optimal features and combinations. 【Result】 Based on CWT, the selected four wavelet features were 595 nm (yellow region) at 6 scales, 614 nm (red region) at 5 scales, 708 nm (near infrared region) at 3 scales, and 754 nm (near infrared region) at 4 scales respectively. The following texture features were selected for the best texture index combination: ENT₇₅₄, MEA₇₅₄, ENT₇₀₈, ENT₅₉₅, ENT₆₁₄, HOM₇₀₈, HOM₅₉₅, HOM₆₁₄, DIS₅₉₅, HOM₇₅₄ and DIS₆₁₄. Besides, it was found that the texture feature MEA₇₅₄ had the superior performance among all the texture, with the highest correlation between the severity of disease and texture (R²=0.67). The PLS-LDA model based on the combination of wavelet feature and texture feature had the highest accuracy, with the overall classification accuracy of 81.17% and the Kappa coefficient of 0.63. In addition, the PLSR model based on spectral index and texture index was the best, and the R ² of modeling and testing was 0.76 and 0.71, respectively. The severity of wheat canopy powdery mildew was about 26% (about 24 days after inoculation), which was identified in this study at the earliest time. 【Conclusion】 The wheat healthy and disease recognition model based on the combination of wavelet feature and texture feature could significantly improve the accuracy of disease classification, and the combination of spectral index and texture index could significantly improve the accuracy and stability of disease severity estimation. The method and results of this study could provide the reference for disease monitoring of other crops and technical support for accurate application of modern intelligent agriculture.

Key words: wheat powdery mildew, canopy, hyperspectral imaging, continuous wavelet transform, texture feature

CAI WeiDi,ZHANG Yu,LIU HaiYan,ZHENG HengBiao,CHENG Tao,TIAN YongChao,ZHU Yan,CAO WeiXing,YAO Xia. Early Detection on Wheat Canopy Powdery Mildew with Hyperspectral Imaging[J].Scientia Agricultura Sinica, 2022, 55(6): 1110-1126.

0
/ / Recommend

Add to citation manager EndNote|Reference Manager|ProCite|BibTeX|RefWorks

URL: https://www.chinaagrisci.com/EN/10.3864/j.issn.0578-1752.2022.06.005

https://www.chinaagrisci.com/EN/Y2022/V55/I6/1110

Figures/Tables 16

Fig. 1

Fig. 2

Table 1

Table 2

Table 3

Fig. 3

Fig. 4

Fig. 5

Table 4

Fig. 6

Table 5

Table 6

Table 7

Table 8

Fig. 7

Table 9

References 64

[18]	MAHLEIN A K, RUMPF T, WELKE P, DEHNE H W, PLUEMER L, STEINER U, OERKE E C. Development of spectral indices for detecting and identifying plant diseases. Remote Sensing of Environment, 2013,128:21-30. doi: 10.1016/j.rse.2012.09.019
[19]	ZHENG Q, HUANG W, CUI X, DONG Y, SHI Y, MA H, LIU L. Identification of wheat yellow rust using optimal three-band spectral indices in different growth stages. Sensors, 2019,19(1):35. doi: 10.3390/s19010035
[20]	王娜. 基于图像处理的玉米叶部病害识别研究[D]. 石河子: 石河子大学, 2009.
	WANG N. Research on maize leaf disease recognition based on image processing[D]. Shihezi: Shihezi University, 2009. (in Chinese)
[21]	昌腾腾. 基于支持向量机的小麦病害识别研究[D]. 泰安: 山东农业大学, 2015.
	CHANG T T. Research on wheat disease recognition based on Support vector Machine[D]. Taian: Shandong Agricultural University, 2015. (in Chinese)
[22]	袁琳. 小麦病虫害多尺度遥感识别和区分方法研究[D]. 杭州: 浙江大学, 2015.
	YUAN L. Identification and differentiation of wheat disease and insects with multi-source and multi-scale remote sensing data[D]. Hangzhou: Zhejiang University, 2015. (in Chinese)
[23]	YAO X, HUANG Y, SHANG G, ZHOU C, CHENG T, TIAN Y, CAO W, ZHU Y. Evaluation of six algorithms to monitor wheat leaf nitrogen concentration. Remote Sensing, 2015,7(11):14939-14966. doi: 10.3390/rs71114939
[24]	ZHOU K, CHENG T, ZHU Y, CAO W, USTIN S L, ZHENG H, YAO X, TIAN Y. Assessing the impact of spatial resolution on the estimation of leaf nitrogen concentration over the full season of paddy rice using near-surface imaging spectroscopy data. Frontiers in Plant Science, 2018,9:964. doi: 10.3389/fpls.2018.00964
[1]	BOWEN K L, EVERTS K L, LEATH S. Reduction in yield of winter wheat in North Carolina due to powdery mildew and leaf rust. Phytopathology, 1991,81(5):503-511. doi: 10.1094/Phyto-81-503
[2]	刘万才, 邵振润. 小麦白粉病流行规律及近年发生概况和分析. 植保技术与推广, 1994,6:17-19.
[25]	MIRIK M, ANSLEY R J, STEDDOM K, RUSH C M, MICHELS G J, WORKNEH F, CUI S, ELLIOTT N C. High spectral and spatial resolution hyperspectral imagery for quantifying Russian wheat aphid infestation in wheat using the constrained energy minimization classifier. Journal of Applied Remote Sensing, 2014,8(1):83661. doi: 10.1117/1.JRS.8.083661
[26]	梁栋, 刘娜, 张东彦. 利用成像高光谱区分冬小麦白粉病与条锈病. 红外与激光工程, 2017,46(1):138004. doi: 10.3788/IRLA
[2]	LIU W C, SHAO Z Z. Epidemiology, occurrence and analysis of wheat powdery mildew in recent years. Plant Protection Technology and Extension, 1994,6:17-19. (in Chinese)
[3]	BINGHAM I J, WALTERS D R, FOULKES M J, PAVELEY N D. Crop traits and the tolerance of wheat and barley to foliar disease. Annals of Applied Biology, 2009,154(2):159-173. doi: 10.1111/aab.2009.154.issue-2
[4]	FOULKES M J, PAVELEY N D, WORLAND A, WELHAM S J, THOMAS J, SNAPE J W. Major genetic changes in wheat with potential to affect disease tolerance. Phytopathology, 2006,96(7):680-688. doi: 10.1094/PHYTO-96-0680
[5]	QIN W C, XUE X Y, ZHANG S M, GU W, WANG B K. Droplet deposition and efficiency of fungicides sprayed with small UAV against wheat powdery mildew. International Journal of Agricultural and Biological Engineering, 2018,11(2):27-32.
[6]	MILNE A, PAVELEY N, AUCLSLEY E, PARSONS D. A model of the effect of fungicides on disease-induced yield loss, for use in wheat disease management decision support systems. Annals of Applied Biology, 2007,151(1):113-125. doi: 10.1111/aab.2007.151.issue-1
[7]	HUSSAIN Z, LEITCH M H. The effect of applied sulphur on the growth, grain yield and control of powdery mildew in spring wheat. Annals of Applied Biology, 2005,147(1):49-56. doi: 10.1111/aab.2005.147.issue-1
[26]	LIANG D, LIU N, ZHANG D Y. Discrimination of powdery mildew and yellow rust of winter wheat using high-resolution hyperspectra and imageries. Infrared and Laser Engineering, 2017,46(1):138004. (in Chinese) doi: 10.3788/IRLA
[27]	刘娜. 基于图像和光谱解析的小麦病害识别研究[D]. 合肥: 安徽大学, 2016.
	LIU N. Recognition of wheat diseases based on imagery and spectral analysis[D]. Hefei: Anhui University, 2016. (in Chinese)
[28]	张东彦, 张竞成, 朱大洲, 王纪华, 罗菊花, 赵晋陵, 黄文江. 小麦叶片胁迫状态下的高光谱图像特征分析研究. 光谱学与光谱分析, 2011,31(4):1101-1105.
	ZHANG D Y, ZHANG J C, ZHU D Z, WANG J H, LUO J H, ZHAO J L, HUANG W J. Investigation of the hyperspectral image characteristics of wheat leaves under different stress. Spectroscopy and Spectral Analysis, 2011,31(4):1101-1105. (in Chinese)
[29]	黄宇. 基于成像高光谱的小麦氮素营养监测研究[D]. 南京: 南京农业大学, 2015.
	HUANG Y. Monitoring nitrogen status with imaging hyperspectral in wheat[D]. Nanjing: Nanjing Agricultural University, 2015. (in Chinese)
[30]	ZHENG H B, CHENG T, ZHOU M, LI D, YAO X, TIAN Y, CAO W, ZHU Y. Improved estimation of rice aboveground biomass combining textural and spectral analysis of UAV imagery. Precision Agriculture, 2019,20(3):611-629. doi: 10.1007/s11119-018-9600-7
[8]	WOLFE M. Trying to understand and control powdery mildew. Plant Pathology, 1984,33(4):451-466. doi: 10.1111/ppa.1984.33.issue-4
[9]	BEEST D E T, PAVELEY N D, SHAW M W, VAN DEN BOSCH F. Disease-weather relationships for powdery mildew and yellow rust on winter wheat. Phytopathology, 2008,98(5):609-617. doi: 10.1094/PHYTO-98-5-0609
[31]	杨燕. 基于高光谱成像技术的水稻稻瘟病诊断关键技术研究[D]. 杭州: 浙江大学, 2012.
	YANG Y. The key diagnosis technology of rice blast based on hyperspectral image[D]. Hangzhou: Zhejiang University, 2012. (in Chinese)
[10]	SHAW M W, POKORNÝ R, LEBEDA A. Preparing for changes in plant disease due to climate change. Plant Protection Science, 2009,45(Special):S3-S10. doi: 10.17221/PPS
[11]	姚树然, 霍治国, 董占强, 李敏, 陈晓静. 基于逐时温湿度的小麦白粉病指标与模型. 生态学杂志, 2013,32(5):1364-1370.
[32]	CHENG T, RIVARD B, SÁNCHEZ-AZOFEIFA A. Spectroscopic determination of leaf water content using continuous wavelet analysis. Remote Sensing of Environment, 2010,115(2):659-670. doi: 10.1016/j.rse.2010.11.001
[33]	ZHANG J C, YUAN L, WANG J H, HUANG W J, CHEN L P, ZHANG D Y. Spectroscopic leaf level detection of powdery mildew for winter wheat using continuous wavelet analysis. Journal of Integrative Agriculture, 2012,11(9):1474-1484. doi: 10.1016/S2095-3119(12)60147-6
[34]	梁栋, 杨勤英, 黄文江, 彭代亮, 赵晋陵, 黄林生, 张东彦, 宋晓宇. 基于小波变换与支持向量机回归的冬小麦叶面积指数估算. 红外与激光工程, 2015,44(1):335-340.
	LIANG D, YANG Q Y, HUANG W J, PENG D L, ZHAO J L, HUANG L S, ZHANG D Y, SONG X Y. Estimation of leaf area index based on wavelet transform and support vector machine regression in winter wheat. Infrared Laser Engineering, 2015,44(1):335-340. (in Chinese)
[11]	YAO S R, HUO Z G, DONG Z Q, LI M, CHEN X J. Indices and modeling of wheat powdery mildew epidemic based on hourly air temperature and humidity data. Chinese Journal of Ecology, 2013,32(5):1364-1370. (in Chinese)
[12]	CAUBEL J, LAUNAY M, RIPOCHE D, GOUACHE D, BUIS S, HUARD F, HUBER L, BRUN F, BANCAL M O. Climate change effects on leaf rust of wheat: Implementing a coupled crop-disease model in a French regional application. European Journal of Agronomy, 2017,90:53-66. doi: 10.1016/j.eja.2017.07.004
[35]	SINGH S K, HOYOS-VILLEGAS V, RAY J D, SMITH J R, FRITSCHI F B. Quantification of leaf pigments in soybean (Glycine max (L.) Merr.) based on wavelet decomposition of hyperspectral features. Field Crops Research, 2013,149:20-32. doi: 10.1016/j.fcr.2013.04.019
[36]	LIAO Q, WANG J, YANG G, ZHANG D, LII H, FU Y, LI Z. Comparison of spectral indices and wavelet transform for estimating chlorophyll content of maize from hyperspectral reflectance. Journal of Applied Remote Sensing, 2013,7(1):73575. doi: 10.1117/1.JRS.7.073575
[13]	ZHANG J CH, PU R L, YUAN L, HUANG W J, YANG G J. Integrating remotely sensed and meteorological observations to forecast wheat powdery mildew at a regional scale. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2014,7(11):4328-4339. doi: 10.1109/JSTARS.4609443
[14]	MAHLEIN A K, OERKE E C, STEINER U, DEHNE H W. Recent advances in sensing plant diseases for precision crop protection. European Journal of Plant Pathology, 2012,133(1):197-209. doi: 10.1007/s10658-011-9878-z
[37]	PU R, GONG P. Wavelet transform applied to EO-1 hyperspectral data for forest LAI and crown closure mapping. Remote Sensing of Environment, 2004,91(2):212-224. doi: 10.1016/j.rse.2004.03.006
[38]	SHI Y, HUANG W, GONZÁLEZ-MORENO P, LUKE B, DONG Y, ZHENG Q, MA H, LIU L. Wavelet-based rust spectral feature set (wrsfs): A novel spectral feature set based on continuous wavelet transformation for tracking progressive host-pathogen interaction of yellow rust on wheat. Remote Sensing, 2018,10(4):525. doi: 10.3390/rs10040525
[15]	MARTINELLI F, SCALENGHE R, DAVINO S, PANNO S, SCUDERI G, RUISI P, VILLA P, STROPPIANA D, BOSCHETTI M, GOULART L R, DAVIS C E, DANDEKAR A M. Advanced methods of plant disease detection. A review. Agronomy for Sustainable Development, 2015,35(1):1-25. doi: 10.1007/s13593-014-0246-1
[16]	CAO X R, LUO Y, ZHOU Y L, DUAN X Y, CHENG D F. Detection of powdery mildew in two winter wheat cultivars using canopy hyperspectral reflectance. Crop Protection, 2013,45:124-131. doi: 10.1016/j.cropro.2012.12.002
[39]	LICHTENTHALER H K. Chlorophylls and carotenoids: pigments of photosynthetic biomembranes. Methods in Enzymology, 1987,148C(1):350-382.
[40]	ZHANG J C, WANG B, ZHANG X X, LIU P, DONG Y Y, WU K H, HUANG W J. Impact of spectral interval on wavelet features for detecting wheat yellow rust with hyperspectral data. International Journal of Agricultural and Biological Engineering, 2018,11(6):138-144.
[17]	FENG W, SHEN W, HE L, DUAN J, GUO B, LI Y, WANG C, GUO T. Improved remote sensing detection of wheat powdery mildew using dual-green vegetation indices. Precision Agriculture, 2016,17(5):608-627. doi: 10.1007/s11119-016-9440-2
[41]	HARALICK R M, SHANMUGAM K. Textural features for image classification. IEEE Transactions on Systems, Man, and Cybernetics, 1973,3(6):610-621.
[42]	FENG W, QI S L, HENG Y R, ZHOU Y, WU Y P, LIU W D, HE L, LI X. Canopy vegetation indices from in situ hyperspectral data to assess plant water status of winter wheat under powdery mildew stress. Front Plant Science, 2017,8:1219. doi: 10.3389/fpls.2017.01219
[43]	杜世州. 基于多源数据小麦白粉病遥感监测研究[D]. 合肥: 安徽农业大学, 2013.
	DU S Z. Research on wheat powdery mildew monitoring based on Multi-source remote sensing data[D]. Hefei: Anhui University, 2013. (in Chinese)
[44]	王文雁. 基于高光谱的小麦白粉病监测研究[D]. 南京: 南京农业大学, 2016.
	WANG W Y. Monitoring powdery mildew with hyperspectral reflectance in wheat[D]. Nanjing: Nanjing Agricultural University, 2016. (in Chinese)
[45]	WOLD S, MARTENS H, WOLD H. The Multivariate Calibration Problem in Chemistry Solved by the PLS Method. Matrix pencils. Springer Berlin Heidelberg, 1983: 286-293.
[46]	ORTIZ M C, SARABIA L A, SYMINGTON C. Analysis of ageing and typification of vintage ports by partial least squares and soft independent modelling class analogy. Analyst, 1996,121(8):1009-1013. doi: 10.1039/AN9962101009
[47]	DELWICHE S R, CHEN Y R, HRUSCHKA W R. Differentiation of hard red wheat by near-infrared analysis of bulk samples. Cereal Chemistry, 1995,72(3):243-247.
[48]	BARKER M, RAYENS W. Partial least squares for discrimination. Journal of Chemometrics, 2003,17(3):166-173. doi: 10.1002/(ISSN)1099-128X
[49]	HUANG W J, GUAN Q S, LUO J H, ZHANG J C, ZHAO J L, LIANG D, HUANG L S, ZHANG D Y. New optimized spectral indices for identifying and monitoring winter wheat diseases. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2014,7(6):2516-2524. doi: 10.1109/JSTARS.4609443
[50]	CHEN B, WANG K, LI S, WANG J, BAI J, XIAO C, LAI J. Spectrum characteristics of cotton canopy infected with verticillium wilt and inversion of severity level. Computer and Computing Technologies in Agriculture, 2008,2:1169-1180.
[51]	GAMON J A, PENUELAS J, FIELD C B. A narrow-waveband spectral index that tracks diurnal changes in photosynthetic efficiency. Remote Sensing of Environment, 1992,41(1):35-44. doi: 10.1016/0034-4257(92)90059-S
[52]	DAUGHTRY C S T, WALTHALL C L, KIM M S, DE COLSTOUN E B, MCMURTREY J E. Estimating corn leaf chlorophyll concentration from leaf and canopy reflectance. Remote Sensing of Environment, 2000,74(2):229-239. doi: 10.1016/S0034-4257(00)00113-9
[53]	LEWIS H G, BROWN M. A generalized confusion matrix for assessing area estimates from remotely sensed data. International Journal of Remote Sensing, 2001,22(16):3223-3235. doi: 10.1080/01431160152558332
[54]	PENUELAS J, BARET F, FILELLA I. Semiempirical indexes to assess carotenoids chlorophyll-a ratio from leaf spectral reflectance. Photosynthetica, 1995,31(2):221-230.
[55]	MERTON R, HUNTINGTON J. Early simulation results of the ARIES-1 satellite sensor for multi-temporal vegetation research derived from AVIRIS. Proceedings of the Eighth Annual JPL Airborne Earth Science Workshop, Pasadena, CA, USA, 1999: 9-11.
[56]	WOLD S, SJÖSTRÖM M, ERIKSSON L. PLS-regression: A basic tool of chemometrics. Chemometrics and Intelligent Laboratory Systems, 2001,58(2):109-130. doi: 10.1016/S0169-7439(01)00155-1
[57]	ZHANG J C, PU R L, WANG J H, YUAN L, LUO J H. Detecting powdery mildew of winter wheat using leaf level hyperspectral measurements. Computers and Electronics in Agriculture, 2012,85:13-23. doi: 10.1016/j.compag.2012.03.006
[58]	ZHANG J, PU R, LORAAMM R W, YANG G, WANG J. Comparison between wavelet spectral features and conventional spectral features in detecting yellow rust for winter wheat. Computers and Electronics in Agriculture, 2014,100:79-87. doi: 10.1016/j.compag.2013.11.001
[59]	SHI Y, HUANG W J, ZHOU X F. Evaluation of wavelet spectral features in pathological detection and discrimination of yellow rust and powdery mildew in winter wheat with hyperspectral reflectance data. Journal of Applied Remote Sensing, 2017,11(2):26025. doi: 10.1117/1.JRS.11.026025
[60]	CAO X R, LUO Y, ZHOU Y L, ZHOU Y L, DUAN X Y, CHENG D F. Detection of powdery mildew in two winter wheat cultivars using canopy hyperspectral reflectance. Crop Protection, 2013,45:124-131. doi: 10.1016/j.cropro.2012.12.002
[61]	郑恒彪. 水稻生育期及生长参数的近地面遥感监测研究[D]. 南京: 南京农业大学, 2018.
	ZHENG H B. Monitoring rice phenology and growth parameters using near-ground remote sensing platforms[D]. Nanjing: Nanjing Agricultural University, 2018. (in Chinese)
[62]	LU D. Aboveground biomass estimation using Landsat TM data in the Brazilian Amazon. International Journal of Remote Sensing, 2005,26(12):2509-2525. doi: 10.1080/01431160500142145
[63]	WULDER M, FRANKLIN S, LAVIGNE M. High spatial resolution optical image texture for improved estimation of forest stand leaf area index. Canadian Journal of Remote Sensing, 1996,22(4):441-449. doi: 10.1080/07038992.1996.10874668
[64]	WULDER M A, LEDREW E F, FRANKLIN S E, LAVIGNE M B. Aerial image texture information in the estimation of northern deciduous and mixed wood forest leaf area index (LAI). Remote Sensing of Environment, 1998,64(1):64-76. doi: 10.1016/S0034-4257(97)00169-7

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed

Comments

Recommended 0

No Suggested Reading articles found!

名称Name	函数表达式Function expression	描述Description
均值 Mean, MEA	$\sum_{i, j=0}^{N=j} i \times P_{i, j}$	反映了灰度平均值情况 Reflect the gray mean value
方差 Variance, VAR	$\sum\limits_{i,j=0}^{N-1}{i\times {{P}_{i,j}}{{(i-MEA)}^{2}}}$	反映了灰度变化的大小Reflect the change of grayscale
均一性 Homogeneity, HOM	$\sum_{i=0}^{N-1} \sum_{j=0}^{N-1} P_{i, j} P_{i, j} /\left[1+(i+j)^{2}\right]$	反映了纹理局部同质性Reflect local homogeneity of texture
对比度 Contrast, CON	$\sum_{n=0}^{N-1} n^{2}\left\{\sum_{i=0}^{N-1} \sum_{\substack{j=0 \\\|i-j\|=n}}^{N-1} P_{i, j}\right\}$	反映了纹理的清晰度Reflect texture sharpness
异质性 Dissimilarity, DIS	$\sum_{i, j=0}^{N-1} i \times P_{i, j}\|i-j\|$	反映纹理的相似性Reflect texture similarity
熵 Entropy, ENT	$\sum_{i=0}^{N-1} \sum_{j=0}^{N-1} P_{i, j} \log P_{i, j}$	反映图像具有的信息量Reflect the amount of image information
角二阶矩 Second Moment, SEM	$\sum_{i, j=0}^{N=j} i \times P_{i, j}^{2}$	反映了图像灰度分布的均匀性 Reflect the uniformity of image gray distribution
相关性 Correlation, COR	$\left[\sum_{i=0}^{N-1} \sum_{j=0}^{N-1} i j P_{i, j}-u_{1} u_{2}\right] / \sigma_{1} \sigma_{2}$	反映某种灰度值沿某个方向的延伸长度 Reflect the extension length of some gray value along a certain direction

定义 Definition	方程 Equation	相关生理参数 Relative physical parameter
白粉病指数 Powdery mildew index, PMI	(R₅₁₅-R₆₉₈)/(R₅₁₅+R₆₉₈)-0.5×R₇₃₈	小麦病害Wheat disease^[49]
简单修改比 Modified simple ratio, MSR	(R₈₀₀/R₆₇₀ -1)/ (R₈₀₀/R₆₇₀ + 1)1/2	叶面积Leaf area^[50]
光化学反射指数 Photochemical reflectance index, PRI	(R₅₇₀- R₅₃₁)/ (R₅₇₀ + R₅₃₁)	光合辐射Photosynthetic radiation^[51]
光合辐射 Photosynthetic radiation, PhRI	(R₅₅₀ - R₅₃₁)/ (R₅₅₀+ R₅₃₁)	光合利用效率Light use efficiency^[51]
改进的叶绿素吸收比指数 Modified chlorophyll absorption ratio index, MCARI	[(R₇₀₁-R₆₇₁)-0.2(R₇₀₁-R₅₄₉)]/(R₇₀₁/R₆₇₁)	叶绿素吸收Chlorophyll absorption^[52]
花青素反射指数 Anthocyanin reflectance index, ARI	R₅₅₀^-1-R₇₀₀^-1	花青素含量Anthocyanin content^[53]
与结构无关的色素指数 Structure independent pigment index, SIPI	(R₈₀₀ - R₄₄₅)/(R₈₀₀ - R₆₈₀)	色素含量Pigment content^[54]
归一化色素叶绿素比值指数 Normalized pigment chlorophyll ration index, NPCI	(R₆₈₀- R₄₃₀)/(R₆₈₀ + R₄₃₀)	叶绿素比值Chlorophyll ratio^[54]
红边植被胁迫指数 Red-edge vegetation stress index, RVSI	[(R₇₁₂ + R₇₅₂)/2] - R₇₃₂	生物量Biomass^[55]

光谱区域 Spectral region	入选波段 Selected wavelength	尺度 Scale	决定系数 R²
黄光区域Yellow region	595	6	0.82
红光区域Red region	614	5	0.83
近红外区域Near infrared region	708	3	0.85
近红外区域Near infrared region	754	4	0.84

模型 Model	纹理指数 Texture index	入选纹理 Selected texture		决定系数 Determinant (R²)
模型 Model	纹理指数 Texture index	T1	T2	决定系数 Determinant (R²)
线性模型 Linear model	NDTI (T1, T2)	ENT₇₅₄	MEA₇₅₄	0.51
		MEA₇₅₄	ENT₇₀₈	0.50
		MEA₇₅₄	ENT₅₉₅	0.50
		MEA₇₅₄	ENT₆₁₄	0.50
		MEA₇₅₄	HOM₇₀₈	0.47
		MEA₇₅₄	HOM₅₉₅	0.47
		MEA₇₅₄	HOM₆₁₄	0.46
		HOM₇₅₄	MEA₇₅₄	0.46
		MEA₇₅₄	DIS₅₉₅	0.46
		MEA₇₅₄	DIS₆₁₄	0.45

纹理特征 Texture feature	小波特征 Wavelet feature
纹理特征 Texture feature	595 nm	614 nm	708 nm	754 nm
均值 MEA	0.00ns	0.00ns	0.01ns	0.67***
方差 VAR	0.29***	0.31***	0.29***	0.01ns
均一性 HOM	0.25**	0.23**	0.27**	0.27**
对比度 CON	0.27***	0.29***	0.27***	0.01ns
异质性 DIS	0.28**	0.30***	0.28***	0.08**
熵 ENT	0.30ns	0.26ns	0.35ns	0.38ns
角二阶矩 SEM	0.28***	0.27***	0.28***	0.28***
相关性 COR	0.01ns	0.02ns	0.03ns	0.01ns

Early Detection on Wheat Canopy Powdery Mildew with Hyperspectral Imaging

RichHTML

PDF

Abstract

Cite this article

share this article

Figures/Tables 16

References 64

Related Articles 15

Metrics

Comments

Recommended 0

2018	测试日期 Test date
2018	04-09	04-17	04-19	04-25	04-28	05-03	05-09
接种后天数DAI	8	16	18	24	27	32	38
样本数量Sample number	14	13	14	14	14	14	13
2017	测试日期 Test date
2017	03-27	04-01	04-13	04-22	04-28	05-10
接种后天数DAI	6	11	23	32	38	50
样本数量Sample number	6	6	10	12	12	12

输入特征 Input feature	特征数量 Number of features	分类精度 Classification accuracy (%)		总体分类精度 OAA (%)	卡帕系数 Kappa
输入特征 Input feature	特征数量 Number of features	健康 Healthy	感病 Infected	总体分类精度 OAA (%)	卡帕系数 Kappa
小波特征与纹理特征结合 WFs & TFs	36	92.54	72.41	81.17	0.63
光谱指数 VIs	9	89.55	70.11	78.57	0.58
光谱指数与纹理指数结合 VIs & NDTIs	19	86.57	71.26	77.92	0.56
纹理特征 TFs	32	85.07	71.26	77.27	0.55
纹理指数 NDTIs	10	77.61	70.11	73.38	0.47
小波特征 WFs	4	82.09	64.37	72.08	0.45

输入特征 Input feature	特征数量 Number of features	建模 Calibration		检验 Validation
输入特征 Input feature	特征数量 Number of features	R²	RMSE	R²	RMSE	RRMSE
小波特征与纹理特征结合WFs & TFs	36	0.8	8.13	0.68	11.84	0.39
光谱指数VIs	9	0.76	8.70	0.69	11.54	0.38
光谱指数与纹理指数结合VIs & NDTIs	19	0.76	8.89	0.71	11.30	0.38
纹理特征TFs	32	0.72	9.42	0.42	15.94	0.53
小波特征WFs	4	0.64	9.72	0.61	12.93	0.43
纹理指数NDTIs	10	0.59	9.85	0.47	15.31	0.51

年份 Year	分类精度 Classification accuracy (%)
年份 Year		8d(7.4%)	16d(15.9%)	18d(26.2%)	24d(27.7%)	27d(32.3%)	32d(41.7%)	38d(63.2%)
2018	健康Healthy	83.33	100	83.33	100	100	100	100
	感病Infected	75.00	100	75.00	100	100	100	100
	Kappa	0.57	0.56	0.57	0.84	1	1	1
		6d(1.5%)	11d(8.9%)	23d(25.2%)	32d(26.2%)	38d(33%)	50d(33%)
2017	健康Healthy	66.67	61.67	71.67	100	100	100
	感病Infected	66.67	75.00	77.50	100	100	100
	Kappa	0.33	0.5	0.55	0.85	1	1

[1]	HaiYu TAO,AiWu ZHANG,HaiYang PANG,XiaoYan KANG. Smart-Phone Application in Situ Grassland Biomass Estimation [J]. Scientia Agricultura Sinica, 2021, 54(5): 933-944.
[2]	ZHU ZhiFeng,LIU Ping,XU RangWei,CHEN ChuanWu,DENG ChongLing,NIU Ying,ZHU Yi,WANG PengWei,DENG XiuXin,CHENG YunJiang. Influence of Plastic Film Covering of Tree Canopy on Fruit Postharvest Storage Performance in Shatangju Tangerine [J]. Scientia Agricultura Sinica, 2021, 54(12): 2630-2643.
[3]	LI MeiXuan,ZHU XiCun,BAI XueYuan,PENG YuFeng,TIAN ZhongYu,JIANG YuanMao. Remote Sensing Inversion of Nitrogen Content in Apple Canopy Based on Shadow Removal in UAV Multi-Spectral Remote Sensing Images [J]. Scientia Agricultura Sinica, 2021, 54(10): 2084-2094.
[4]	YIN Wen,CHAI Qiang,YU AiZhong,ZHAO Cai,FAN ZhiLong,HU FaLong,FAN Hong,GUO Yao. Effects of Intercropped Wheat Straw Retention on Canopy Temperature and Photosynthetic Physiological Characteristics of Intercropped Maize Mulched with Plastic During Grain Filling Stage [J]. Scientia Agricultura Sinica, 2020, 53(23): 4764-4776.
[5]	LI Jing,WANG HongZhang,XU JiaYi,LIU Peng,ZHANG JiWang,ZHAO Bin,REN BaiZhao. Effects of Different Cultivation Modes on Canopy Structure and Photosynthetic Performance of Summer Maize [J]. Scientia Agricultura Sinica, 2020, 53(22): 4550-4560.
[6]	DING XiangPeng,BAI Jing,ZHANG ChunYu,ZHANG JiWang,LIU Peng,REN BaiZhao,ZHAO Bin. Effects of Line-Spacing Expansion and Row-Spacing Shrinkage on Population Structure and Yield of Summer Maize [J]. Scientia Agricultura Sinica, 2020, 53(19): 3915-3927.
[7]	XIANG FangLin,LI XinGe,MA JiFeng,LIU XiaoJun,TIAN YongChao,ZHU Yan,CAO WeiXing,CAO Qiang. Using Canopy Time-Series Vegetation Index to Predict Yield of Winter Wheat [J]. Scientia Agricultura Sinica, 2020, 53(18): 3679-3692.
[8]	PIAO Lin,LI Bo,CHEN XiChang,DING ZaiSong,ZHANG Yu,ZHAO Ming,LI CongFeng. Regulation Effects of Improved Cultivation Measures on Canopy Structure and Yield Formation of Dense Spring Maize Population [J]. Scientia Agricultura Sinica, 2020, 53(15): 3048-3058.
[9]	BAI YanWen,ZHANG HongJun,ZHU YaLi,ZHENG XueHui,YANG Mei,LI CongFeng,ZHANG RenHe. Responses of Canopy Radiation and Nitrogen Distribution, Leaf Senescence and Radiation Use Efficiency on Increased Planting Density of Different Variety Types of Maize [J]. Scientia Agricultura Sinica, 2020, 53(15): 3059-3070.
[10]	ZHOU LongFei, GU XiaoHe, CHENG Shu, YANG GuiJun, SUN Qian, SHU MeiYan. Spectral Diagnosis of Leaf Area Density of Maize at Heading Stage Under Lodging Stress [J]. Scientia Agricultura Sinica, 2019, 52(9): 1518-1528.
[11]	YanChuan MA,Hao LIU,ZhiFang CHEN,Kai ZHANG,Xuan YU,JingLei WANG,JingSheng SUN. Canopy Equivalent Water Thickness Estimation of Cotton Based on Hyperspectral Index [J]. Scientia Agricultura Sinica, 2019, 52(24): 4470-4483.
[12]	Peng LI,Ming ZHANG,XiangSheng DAI,Teng WANG,YongQiang ZHENG,ShiLai YI,Qiang LÜ. Real-Time Estimation of Citrus Canopy Volume Based on Laser Scanner and Irregular Triangular Prism Module Method [J]. Scientia Agricultura Sinica, 2019, 52(24): 4493-4504.
[13]	SUN Qian,GU XiaoHe,SUN Lin,WANG Miao,ZHOU LongFei,YANG GuiJun,LI WeiGuo,SHU MeiYan. Spectral Response Analysis of Canopy Water Content of Winter Wheat Under Different Irrigation Conditions [J]. Scientia Agricultura Sinica, 2019, 52(14): 2425-2435.
[14]	CHEN PengFei, LIANG Fei. Cotton Nitrogen Nutrition Diagnosis Based on Spectrum and Texture Feature of Images from Low Altitude Unmanned Aerial Vehicle [J]. Scientia Agricultura Sinica, 2019, 52(13): 2220-2229.
[15]	XIAO JiBing,LIU Zhi,KONG FanXin,XIN ZongXu,WU HongSheng. Effects of Planting Pattern and Density on Population Structure and Yield of Sorghum [J]. Scientia Agricultura Sinica, 2018, 51(22): 4264-4276.